© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249201
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    آور
    0.46
     vitth
    0.45
    镓
    0.44
    Invoke
    0.44
    RawO
    0.43
    IVACON
    0.43
    servicetime
    0.43
    InnerHTML
    0.43
     Всё
    0.42
     มาก
    0.42
    POSITIVE LOGITS
     neurology
    0.52
     laboratory
    0.52
    1
    0.51
     Board
    0.51
     dike
    0.50
     board
    0.50
    ユーザー
    0.49
     dermatology
    0.49
     laboratorium
    0.48
     Laboratory
    0.47
    Activations Density 0.001%

    No Known Activations